Automated Framework to Evaluate and Harden LLM System Instructions against Encoding Attacks

System Instructions in Large Language Models LLMs are commonly used to enforce safety policies, define agent behavior, and protect sensitive operational context in agentic AI applications. These instructions may contain sensitive information such as API credentials, internal policies, and...

When Labels Are Scarce: A Systematic Mapping of Label-Efficient Code Vulnerability Detection

Machine-learning-based code vulnerability detection CVD has progressed rapidly, from deep program representations to pretrained code models and LLM-centered pipelines. Yet dependable vulnerability labeling remains expensive, noisy, and uneven across projects, languages, and CWE types, motivating...

CVE-2026-28505 Tautulli: RCE via eval() sandbox bypass using lambda nested scope to escape co_names whitelist check

Tautulli is a Python based monitoring and tracking tool for Plex Media Server. Prior to version 2.17.0, the streval function in notificationhandler.py implements a sandboxed eval for notification text templates. The sandbox attempts to restrict callable names by inspecting code.conames of the...

Why Aggregate Accuracy Is Inadequate for Evaluating Fairness in Law Enforcement Facial Recognition Systems

Facial recognition systems are increasingly deployed in law enforcement and security contexts, where algorithmic decisions can carry significant societal consequences. Despite high reported accuracy, growing evidence demonstrates that such systems often exhibit uneven performance across demograph...

OpenFeature evaluation API reads input data with no bounds

The OpenFeature feature toggle evaluation endpoint reads unbounded values into memory, which can cause out-of-memory crashes...

Design Principles for the Construction of a Benchmark Evaluating Security Operation Capabilities of Multi-Agent AI Systems

As Large Language Models LLMs and multi-agent AI systems are demonstrating increasing potential in cybersecurity operations, organizations, policymakers, model providers, and researchers in the AI and cybersecurity communities are interested in quantifying the capabilities of such AI systems to...

CVE-2026-4851

GRID::Machine (Perl) up to version 0.127 is affected by arbitrary code execution due to unsafe deserialization in read_operation() where $arg is deserialized via eval(); a compromised remote host can inject Perl code in the Dumper-formatted response, executing on the client with every RPC call. T...

CVE-2026-33729

OpenFGA is a high-performance and flexible authorization/permission engine built for developers and inspired by Google Zanzibar. In versions prior to 1.13.1, under specific conditions, models using conditions with caching enabled can result in two different check requests producing the same cache...

CVE-2026-33494

ORY Oathkeeper is an Identity & Access Proxy IAP and Access Control Decision API that authorizes HTTP requests based on sets of Access Rules. Versions prior to 26.2.0 are vulnerable to an authorization bypass via HTTP path traversal. An attacker can craft a URL containing path traversal sequences...

CVE-2026-33631

ClearanceKit intercepts file-system access events on macOS and enforces per-process access policies. In versions on the 4.1 branch and earlier, the opfilter Endpoint Security system extension enforced file access policy exclusively by intercepting ESEVENTTYPEAUTHOPEN events. Seven additional file...

CVE-2026-4963 huggingface smolagents Incomplete Fix CVE-2025-9959 local_python_executor.py evaluate_with code injection

A weakness has been identified in huggingface smolagents 1.25.0.dev0. This affects the function evaluateaugassign/evaluatecall/evaluatewith of the file src/smolagents/localpythonexecutor.py of the component Incomplete Fix CVE-2025-9959. This manipulation causes code injection. It is possible to...

EUVD-2026-16598

The OpenFeature feature toggle evaluation endpoint reads unbounded values into memory, which can cause out-of-memory crashes...

CVE-2026-27880

The OpenFeature feature toggle evaluation endpoint reads unbounded values into memory, which can cause out-of-memory crashes...

UBUNTU-CVE-2026-27880

The OpenFeature feature toggle evaluation endpoint reads unbounded values into memory, which can cause out-of-memory crashes...

CVE-2026-27880

CVE-2026-27880 affects Grafana deployments via the OpenFeature feature toggle evaluation endpoint, which reads unbounded input into memory and can cause out-of-memory crashes. Public details in the connected Nessus entry specify affected Grafana versions: 12.1.x before 12.1.10, 12.2.x before 12.2...

CVE-2026-27880 OpenFeature evaluation API reads input data with no bounds

The OpenFeature feature toggle evaluation endpoint reads unbounded values into memory, which can cause out-of-memory crashes...

CVE-2026-27880 OpenFeature evaluation API reads input data with no bounds

The OpenFeature feature toggle evaluation endpoint reads unbounded values into memory, which can cause out-of-memory crashes...

CVE-2026-27880 OpenFeature evaluation API reads input data with no bounds

The OpenFeature feature toggle evaluation endpoint reads unbounded values into memory, which can cause out-of-memory crashes...

Exploit for Eval Injection in Langflow

CVE-2026-33...

CVE-2026-33729 OpenFGA has an Authorization Bypass through cached keys

OpenFGA is a high-performance and flexible authorization/permission engine built for developers and inspired by Google Zanzibar. In versions prior to 1.13.1, under specific conditions, models using conditions with caching enabled can result in two different check requests producing the same cache...